中文
相关论文

相关论文: OpenAL: Evaluation and Interpretation of Active Le…

200 篇论文

With the rise of large language models, neural text summarization has advanced significantly in recent years. However, even state-of-the-art models continue to rely heavily on high-quality human-annotated data for training and evaluation.…

计算与语言 · 计算机科学 2025-03-04 Petros Stylianos Giouroukis , Alexios Gidiotis , Grigorios Tsoumakas

In many applications, data is easy to acquire but expensive and time-consuming to label prominent examples include medical imaging and NLP. This disparity has only grown in recent years as our ability to collect data improves. Under these…

机器学习 · 计算机科学 2021-04-07 Jaya Krishna Mandivarapu , Blake Camp , Rolando Estrada

This paper proposes an active learning (AL) algorithm to solve regression problems based on inverse-distance weighting functions for selecting the feature vectors to query. The algorithm has the following features: (i) supports both…

机器学习 · 计算机科学 2022-12-15 Alberto Bemporad

The availability of labelled data is one of the main limitations in machine learning. We can alleviate this using weak supervision: a framework that uses expert-defined rules $\boldsymbol{\lambda}$ to estimate probabilistic labels…

机器学习 · 计算机科学 2021-05-03 Samantha Biegel , Rafah El-Khatib , Luiz Otavio Vilas Boas Oliveira , Max Baak , Nanne Aben

While annotating decent amounts of data to satisfy sophisticated learning models can be cost-prohibitive for many real-world applications. Active learning (AL) and semi-supervised learning (SSL) are two effective, but often isolated, means…

机器学习 · 计算机科学 2022-06-08 Jiannan Guo , Yangyang Kang , Yu Duan , Xiaozhong Liu , Siliang Tang , Wenqiao Zhang , Kun Kuang , Changlong Sun , Fei Wu

We study a generalization of classical active learning to real-world settings with concrete prediction targets where sampling is restricted to an accessible region of the domain, while prediction targets may lie outside this region. We…

机器学习 · 计算机科学 2025-02-11 Jonas Hübotter , Bhavya Sukhija , Lenart Treven , Yarden As , Andreas Krause

This paper introduces a cost-efficient active learning (AL) framework for classification, featuring a novel query design called candidate set query. Unlike traditional AL queries requiring the oracle to examine all possible classes, our…

机器学习 · 计算机科学 2025-08-20 Yeho Gwon , Sehyun Hwang , Hoyoung Kim , Jungseul Ok , Suha Kwak

We present OpenRL, an advanced reinforcement learning (RL) framework designed to accommodate a diverse array of tasks, from single-agent challenges to complex multi-agent systems. OpenRL's robust support for self-play training empowers…

机器学习 · 计算机科学 2023-12-29 Shiyu Huang , Wentse Chen , Yiwen Sun , Fuqing Bie , Wei-Wei Tu

Active learning for sentence understanding attempts to reduce the annotation cost by identifying the most informative examples. Common methods for active learning use either uncertainty or diversity sampling in the pool-based scenario. In…

计算与语言 · 计算机科学 2022-10-28 Hanshan Zhang , Zhen Zhang , Hongfei Jiang , Yang Song

Deep neural networks have reached high accuracy on object detection but their success hinges on large amounts of labeled data. To reduce the labels dependency, various active learning strategies have been proposed, typically based on the…

计算机视觉与模式识别 · 计算机科学 2021-11-30 Ismail Elezi , Zhiding Yu , Anima Anandkumar , Laura Leal-Taixe , Jose M. Alvarez

Active learning is a practical field of machine learning that automates the process of selecting which data to label. Current methods are effective in reducing the burden of data labeling but are heavily model-reliant. This has led to the…

机器学习 · 计算机科学 2023-03-01 Sai Prathyush Katragadda , Tyler Cody , Peter Beling , Laura Freeman

Active learning (AL) aims to select the most useful data samples from an unlabeled data pool and annotate them to expand the labeled dataset under a limited budget. Especially, uncertainty-based methods choose the most uncertain samples,…

机器学习 · 计算机科学 2023-10-02 Seong Min Kye , Kwanghee Choi , Hyeongmin Byun , Buru Chang

Quantum machine learning, as an extension of classical machine learning that harnesses quantum mechanics, facilitates effiient learning from data encoded in quantum states. Training a quantum neural network typically demands a substantial…

量子物理 · 物理学 2026-02-17 Yongcheng Ding , Yue Ban , Mikel Sanz , José D. Martín-Guerrero , Xi Chen

Machine learning (ML) is increasingly being used in high-stakes applications impacting society. Therefore, it is of critical importance that ML models do not propagate discrimination. Collecting accurate labeled data in societal…

机器学习 · 计算机科学 2020-07-03 Hadis Anahideh , Abolfazl Asudeh , Saravanan Thirumuruganathan

Pool-based sampling in active learning (AL) represents a key framework for an-notating informative data when dealing with deep learning models. In this paper, we present a novel pipeline for pool-based Active Learning. Unlike most previous…

计算机视觉与模式识别 · 计算机科学 2021-06-08 Razvan Caramalau , Binod Bhattarai , Tae-Kyun Kim

Human annotation cost and time remain significant bottlenecks in Natural Language Processing (NLP), with test data annotation being particularly expensive due to the stringent requirement for low-error and high-quality labels necessary for…

计算与语言 · 计算机科学 2026-03-24 Antonio Purificato , Maria Sofia Bucarelli , Andrea Bacciu , Amin Mantrach , Fabrizio Silvestri

Generating labeled training datasets has become a major bottleneck in Machine Learning (ML) pipelines. Active ML aims to address this issue by designing learning algorithms that automatically and adaptively select the most informative…

机器学习 · 计算机科学 2020-04-29 Mina Karzand , Robert D. Nowak

Large Language Model (LLM) agents are increasingly improved through interaction, yet most self-evolution methods adapt either the policy or the learning environment in isolation. We identify this structural gap as \emph{Agent-Environment…

计算与语言 · 计算机科学 2026-05-26 Yihao Hu , Zhihao Wen , Xiujin Liu , Pan Wang , Xin Zhang , Wei Wu

Active Learning methods create an optimized labeled training set from unlabeled data. We introduce a novel Online Active Deep Learning method for Medical Image Analysis. We extend our MedAL active learning framework to present new results…

Active learning (AL) for multiple target models aims to reduce labeled data querying while effectively training multiple models concurrently. Existing AL algorithms often rely on iterative model training, which can be computationally…

机器学习 · 计算机科学 2024-10-03 Sheng-Jun Huang , Yi Li , Yiming Sun , Ying-Peng Tang